ruby/tensorflow_privacy
1
0
Fork 0
forked from 626_privacy/tensorflow_privacy
Code Pull requests Activity

Changes for pylint.

Browse source
This commit is contained in:
Christopher Choquette Choo 2019-06-19 11:14:02 -04:00
parent 56e16f0a15
commit b120d9c5d8
4 changed files with 8 additions and 303 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

280
privacy/bolton/losses.py
View file

@ -317,283 +317,3 @@ class StrongConvexBinaryCrossentropy(
:return:
"""
return L1L2(l2=self.reg_lambda/2)
# class StrongConvexSparseCategoricalCrossentropy(
# losses.CategoricalCrossentropy,
# StrongConvexMixin
# ):
# """
# Strong Convex version of CategoricalCrossentropy loss using l2 weight
# regularization.
# """
#
# def __init__(self,
# reg_lambda: float,
# C: float,
# radius_constant: float,
# from_logits: bool = True,
# label_smoothing: float = 0,
# reduction: str = losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE,
# name: str = 'binarycrossentropy',
# dtype=tf.float32):
# """
# Args:
# reg_lambda: Weight regularization constant
# C: Penalty parameter C of the loss term
# radius_constant: constant defining the length of the radius
# reduction: reduction type to use. See super class
# label_smoothing: amount of smoothing to perform on labels
# relaxation of trust in labels, e.g. (1 -> 1-x, 0 -> 0+x)
# name: Name of the loss instance
# dtype: tf datatype to use for tensor conversions.
# """
# if reg_lambda <= 0:
# raise ValueError("reg lambda: {0} must be positive".format(reg_lambda))
# if C <= 0:
# raise ValueError('c: {0}, should be >= 0'.format(C))
# if radius_constant <= 0:
# raise ValueError('radius_constant: {0}, should be >= 0'.format(
# radius_constant
# ))
#
# self.C = C
# self.dtype = dtype
# self.reg_lambda = tf.constant(reg_lambda, dtype=self.dtype)
# super(StrongConvexSparseCategoricalCrossentropy, self).__init__(
# reduction=reduction,
# name=name,
# from_logits=from_logits,
# label_smoothing=label_smoothing,
# )
# self.radius_constant = radius_constant
#
# def call(self, y_true, y_pred):
# """Compute loss
#
# Args:
# y_true: Ground truth values.
# y_pred: The predicted values.
#
# Returns:
# Loss values per sample.
# """
# loss = super()
# loss = loss * self.C
# return loss
#
# def radius(self):
# """See super class.
# """
# return self.radius_constant / self.reg_lambda
#
# def gamma(self):
# """See super class.
# """
# return self.reg_lambda
#
# def beta(self, class_weight):
# """See super class.
# """
# max_class_weight = self.max_class_weight(class_weight, self.dtype)
# return self.C * max_class_weight + self.reg_lambda
#
# def lipchitz_constant(self, class_weight):
# """See super class.
# """
# max_class_weight = self.max_class_weight(class_weight, self.dtype)
# return self.C * max_class_weight + self.reg_lambda * self.radius()
#
# def kernel_regularizer(self):
# """
# l2 loss using reg_lambda as the l2 term (as desired). Required for
# this loss function to be strongly convex.
# :return:
# """
# return L1L2(l2=self.reg_lambda)
#
# class StrongConvexSparseCategoricalCrossentropy(
# losses.SparseCategoricalCrossentropy,
# StrongConvexMixin
# ):
# """
# Strong Convex version of SparseCategoricalCrossentropy loss using l2 weight
# regularization.
# """
#
# def __init__(self,
# reg_lambda: float,
# C: float,
# radius_constant: float,
# from_logits: bool = True,
# label_smoothing: float = 0,
# reduction: str = losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE,
# name: str = 'binarycrossentropy',
# dtype=tf.float32):
# """
# Args:
# reg_lambda: Weight regularization constant
# C: Penalty parameter C of the loss term
# radius_constant: constant defining the length of the radius
# reduction: reduction type to use. See super class
# label_smoothing: amount of smoothing to perform on labels
# relaxation of trust in labels, e.g. (1 -> 1-x, 0 -> 0+x)
# name: Name of the loss instance
# dtype: tf datatype to use for tensor conversions.
# """
# if reg_lambda <= 0:
# raise ValueError("reg lambda: {0} must be positive".format(reg_lambda))
# if C <= 0:
# raise ValueError('c: {0}, should be >= 0'.format(C))
# if radius_constant <= 0:
# raise ValueError('radius_constant: {0}, should be >= 0'.format(
# radius_constant
# ))
#
# self.C = C
# self.dtype = dtype
# self.reg_lambda = tf.constant(reg_lambda, dtype=self.dtype)
# super(StrongConvexHuber, self).__init__(reduction=reduction,
# name=name,
# from_logits=from_logits,
# label_smoothing=label_smoothing,
# )
# self.radius_constant = radius_constant
#
# def call(self, y_true, y_pred):
# """Compute loss
#
# Args:
# y_true: Ground truth values.
# y_pred: The predicted values.
#
# Returns:
# Loss values per sample.
# """
# loss = super()
# loss = loss * self.C
# return loss
#
# def radius(self):
# """See super class.
# """
# return self.radius_constant / self.reg_lambda
#
# def gamma(self):
# """See super class.
# """
# return self.reg_lambda
#
# def beta(self, class_weight):
# """See super class.
# """
# max_class_weight = self.max_class_weight(class_weight, self.dtype)
# return self.C * max_class_weight + self.reg_lambda
#
# def lipchitz_constant(self, class_weight):
# """See super class.
# """
# max_class_weight = self.max_class_weight(class_weight, self.dtype)
# return self.C * max_class_weight + self.reg_lambda * self.radius()
#
# def kernel_regularizer(self):
# """
# l2 loss using reg_lambda as the l2 term (as desired). Required for
# this loss function to be strongly convex.
# :return:
# """
# return L1L2(l2=self.reg_lambda)
#
#
# class StrongConvexCategoricalCrossentropy(
# losses.CategoricalCrossentropy,
# StrongConvexMixin
# ):
# """
# Strong Convex version of CategoricalCrossentropy loss using l2 weight
# regularization.
# """
#
# def __init__(self,
# reg_lambda: float,
# C: float,
# radius_constant: float,
# from_logits: bool = True,
# label_smoothing: float = 0,
# reduction: str = losses_utils.ReductionV2.SUM_OVER_BATCH_SIZE,
# name: str = 'binarycrossentropy',
# dtype=tf.float32):
# """
# Args:
# reg_lambda: Weight regularization constant
# C: Penalty parameter C of the loss term
# radius_constant: constant defining the length of the radius
# reduction: reduction type to use. See super class
# label_smoothing: amount of smoothing to perform on labels
# relaxation of trust in labels, e.g. (1 -> 1-x, 0 -> 0+x)
# name: Name of the loss instance
# dtype: tf datatype to use for tensor conversions.
# """
# if reg_lambda <= 0:
# raise ValueError("reg lambda: {0} must be positive".format(reg_lambda))
# if C <= 0:
# raise ValueError('c: {0}, should be >= 0'.format(C))
# if radius_constant <= 0:
# raise ValueError('radius_constant: {0}, should be >= 0'.format(
# radius_constant
# ))
#
# self.C = C
# self.dtype = dtype
# self.reg_lambda = tf.constant(reg_lambda, dtype=self.dtype)
# super(StrongConvexHuber, self).__init__(reduction=reduction,
# name=name,
# from_logits=from_logits,
# label_smoothing=label_smoothing,
# )
# self.radius_constant = radius_constant
#
# def call(self, y_true, y_pred):
# """Compute loss
#
# Args:
# y_true: Ground truth values.
# y_pred: The predicted values.
#
# Returns:
# Loss values per sample.
# """
# loss = super()
# loss = loss * self.C
# return loss
#
# def radius(self):
# """See super class.
# """
# return self.radius_constant / self.reg_lambda
#
# def gamma(self):
# """See super class.
# """
# return self.reg_lambda
#
# def beta(self, class_weight):
# """See super class.
# """
# max_class_weight = self.max_class_weight(class_weight, self.dtype)
# return self.C * max_class_weight + self.reg_lambda
#
# def lipchitz_constant(self, class_weight):
# """See super class.
# """
# max_class_weight = self.max_class_weight(class_weight, self.dtype)
# return self.C * max_class_weight + self.reg_lambda * self.radius()
#
# def kernel_regularizer(self):
# """
# l2 loss using reg_lambda as the l2 term (as desired). Required for
# this loss function to be strongly convex.
# :return:
# """
# return L1L2(l2=self.reg_lambda)

4
privacy/bolton/models_test.py
View file

@ -53,7 +53,7 @@ class TestLoss(losses.Loss, StrongConvexMixin):
"""
return _ops.convert_to_tensor_v2(1, dtype=tf.float32)
def beta(self, class_weight):
def beta(self, class_weight): # pylint: disable=unused-argument
"""Beta smoothess
Args:
@ -64,7 +64,7 @@ class TestLoss(losses.Loss, StrongConvexMixin):
"""
return _ops.convert_to_tensor_v2(1, dtype=tf.float32)
def lipchitz_constant(self, class_weight):
def lipchitz_constant(self, class_weight): # pylint: disable=unused-argument
""" L lipchitz continuous
Args:

1
privacy/bolton/optimizers.py
View file

@ -20,7 +20,6 @@ from __future__ import print_function
import tensorflow as tf
from tensorflow.python.keras.optimizer_v2 import optimizer_v2
from tensorflow.python.ops import math_ops
from tensorflow.python import ops as _ops
from privacy.bolton.losses import StrongConvexMixin
_accepted_distributions = ['laplace'] # implemented distributions for noising

26
privacy/bolton/optimizers_test.py
View file

@ -25,7 +25,6 @@ from tensorflow.python.keras.regularizers import L1L2
from tensorflow.python.keras.initializers import constant
from tensorflow.python.keras import losses
from tensorflow.python.keras.models import Model
from tensorflow.python.framework import ops as _ops
from tensorflow.python.framework import test_util
from tensorflow.python import ops as _ops
from absl.testing import parameterized
@ -33,7 +32,6 @@ from privacy.bolton.losses import StrongConvexMixin
from privacy.bolton import optimizers as opt
class TestModel(Model):
"""
Bolton episilon-delta model
@ -69,18 +67,6 @@ class TestModel(Model):
)
# def call(self, inputs):
# """Forward pass of network
#
# Args:
# inputs: inputs to neural network
#
# Returns:
#
# """
# return self.output_layer(inputs)
class TestLoss(losses.Loss, StrongConvexMixin):
"""Test loss function for testing Bolton model"""
def __init__(self, reg_lambda, C, radius_constant, name='test'):
@ -105,7 +91,7 @@ class TestLoss(losses.Loss, StrongConvexMixin):
"""
return _ops.convert_to_tensor_v2(1, dtype=tf.float32)
def beta(self, class_weight):
def beta(self, class_weight): # pylint: disable=unused-argument
"""Beta smoothess
Args:
@ -116,7 +102,7 @@ class TestLoss(losses.Loss, StrongConvexMixin):
"""
return _ops.convert_to_tensor_v2(1, dtype=tf.float32)
def lipchitz_constant(self, class_weight):
def lipchitz_constant(self, class_weight): # pylint: disable=unused-argument
""" L lipchitz continuous
Args:
@ -217,7 +203,7 @@ class BoltonOptimizerTest(keras_parameterized.TestCase):
model.layers[0].kernel = \
model.layers[0].kernel_initializer((model.layer_input_shape[0],
model.n_outputs))
bolton._is_init = True
bolton._is_init = True # pylint: disable=protected-access
bolton.layers = model.layers
bolton.epsilon = 2
bolton.noise_distribution = 'laplace'
@ -279,7 +265,7 @@ class BoltonOptimizerTest(keras_parameterized.TestCase):
model.layers[0].kernel = \
model.layers[0].kernel_initializer((model.layer_input_shape[0],
model.n_outputs))
bolton._is_init = True
bolton._is_init = True # pylint: disable=protected-access
bolton.layers = model.layers
bolton.epsilon = 2
bolton.noise_distribution = 'laplace'
@ -431,7 +417,7 @@ class BoltonOptimizerTest(keras_parameterized.TestCase):
model.layers[0].kernel = \
model.layers[0].kernel_initializer((model.layer_input_shape[0],
model.n_outputs))
bolton._is_init = True
bolton._is_init = True # pylint: disable=protected-access
bolton.layers = model.layers
bolton.epsilon = 2
bolton.noise_distribution = 'laplace'
@ -467,7 +453,7 @@ class BoltonOptimizerTest(keras_parameterized.TestCase):
model.layers[0].kernel = \
model.layers[0].kernel_initializer((model.layer_input_shape[0],
model.n_outputs))
bolton._is_init = True
bolton._is_init = True # pylint: disable=protected-access
bolton.noise_distribution = 'laplace'
bolton.epsilon = 1
bolton.layers = model.layers